INDEX

Explanations

classifications and categorizations related to academic subjects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

classification systems and codes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ImageContext

-0.60

PostExecute

-0.48

pyx

-0.46

pulumi

-0.45

 Therapies

-0.42

 AXIS

-0.42

綽

-0.42

 UserDetails

-0.42

 intStringLen

-0.42

 Feminism

-0.41

POSITIVE LOGITS

setVerticalGroup

0.50

SerializedSize

0.48

УДК

0.47

الدراسه

0.46

Népesség

0.46

المناصب

0.45

ंदीखरीदारी

0.44

 classifica

0.44

 classification

0.43

PACS

0.43

Activations Density 0.001%

classifications and categorizations related to academic subjects

classification systems and codes

No Comments

No Known Activations